HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

nemo-nano-codec-22khz-1.89kbps-21.5fps

nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps

kind
original
quant
bf16 (16-bit)
family
misc
modality
feature-extraction
root model
nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps
provider
nvidia
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
19,795
likes
15
created
—
last modified
2025-08-30T15:50:27+00:00 (2025)
huggingface
https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps
tags
nemofeature-extractionarxiv:2508.05835arxiv:2010.05646arxiv:2309.15505arxiv:2306.06546arxiv:2409.12117license:otherregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
MOSspeech-tts4.43low| MLS | 4.427 | 2.837 | 0.150 | 0.854 | 2.434 |
WER MLSspeech-asr4.43MLSmedium| MLS | 4.427 | 2.837 | 0.150 | 0.854 | 2.434 |
CERspeech-asr2.43low| MLS | 4.427 | 2.837 | 0.150 | 0.854 | 2.434 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.